Announcement

Collapse
No announcement yet.
X
  • Filter
  • Time
  • Show
Clear All
new posts

  • Time Fixed Effects with Interaction: What is the reference?

    Hi everyone, hope you having a great week.

    I'm having trouble reading the following xtreg output. I've got a treated group (CC=1) and an untreated group (CC=0) and I'm trying to compare the week fixed effects to tell what the difference is.

    In the xtreg line I generated this interaction variable this way: ib0.CC#ib33.Week
    Thus, the default group should be the non-treated group in week 33, which appears to be consistent with the following output.

    My question: for all of the values under '1 34' and '1 35' ...are these coefficient changes from CC=0 and Week =33 (Case1), or are they changes from CC=0 with the same corresponding week? IE, '1 35' is the change in the coefficient from the untreated group week effect in Week 35 (Case 2)?

    In Case1, all of this output is with respect to the Non-treated group in Week 33. Thus, the weekly fixed effect for '1 35' would be -0.0007 below the untreated group in Week 33 (which is omitted).
    In Case 2, the total coeff. for '1 35' would be 0.0033 (CC=0, Week35) - 0.0007 (CC=1, Week35) for a total weekly fixed effect of +0.0026.

    I think it should be Case1, but I'm not confident. Thanks for any and all help.

    This is the output that I have:

    Click image for larger version

Name:	Capture.JPG
Views:	1
Size:	75.2 KB
ID:	1483744

  • #2
    Robert:
    Case1 is correct.
    Kind regards,
    Carlo
    (Stata 18.0 SE)

    Comment


    • #3
      Thank you, Carlo!

      Comment

      Working...
      X